Building prediction models with grouped data: A case study on the prediction of turnover intention
本文面向HR专业人士和研究者，系统介绍预测分析逻辑，并针对HRM中常见的分组数据问题，比较不同建模策略，发现随机效应袋装树模型预测离职意向最准确，关键预测因素包括公平感、领导成员交换等。
Abstract The availability of big data spurred the application of modern prediction analytics (e.g., machine learning methods) in human resource management (HRM) research and practice. Due to the novel and technical nature of prediction analytics, HR professionals and researchers may struggle to collaborate with data experts. We offer a comprehensive introduction to the logic and value of prediction methods. Moreover, we highlight the concern of treating grouped data—commonly seen in HRM research yet rarely discussed in building prediction models. We introduce different strategies to deal with grouped data in applying prediction models. The performance of different modelling approaches and prediction models are compared in an empirical data set consisting of 1454 employees from 199 small and medium sized enterprise's. Following a workflow to compare the relative performance of the prediction models, the model with the best prediction accuracy was the random‐effects bagged tree that allows for complex relationships and incorporates random effects. Following the estimates of this model, we identified the five most influential predictors of turnover intention: perceived fairness, leader‐member exchange, career opportunities, pay satisfaction and age. The inductive nature of prediction models is expected to advance theory development and HR analytics for developing effective HRM policies.